Deep Learning-Based Method to Recognize Line Objects and Flow Arrows from Image-Format Piping and Instrumentation Diagrams for Digitization

As part of research on technology for automatic conversion of image-format piping and instrumentation diagram (P&ID) into digital P&ID, the present study proposes a method for recognizing various types of lines and flow arrows in image-format P&ID. The proposed method consists of three steps. In the first step of preprocessing, the outer border and title box in the diagram are removed. In the second step of detection, continuous lines are detected, and then line signs and flow arrows indicating the flow direction are detected. In the third step of post-processing, using the results of line sign detection, continuous lines that require changing of the line type are determined, and the line types are adjusted accordingly. Then, the recognized lines are merged with flow arrows. For verification of the proposed method, a prototype system was used to conduct an experiment of line recognition. For the nine test P&IDs, the average precision and recall were 96.14% and 89.59%, respectively, showing high recognition performance.

[1]  Moongu Jeon,et al.  Key Points Estimation and Point Instance Segmentation Approach for Lane Detection , 2020, ArXiv.

[2]  Duhwan Mun,et al.  Deep-learning-based recognition of symbols and texts at an industrially applicable level from images of high-density piping and instrumentation diagrams , 2021, Expert Syst. Appl..

[3]  Siyu Zhu,et al.  CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Peng Liu,et al.  A review of lane detection methods based on deep learning , 2021, Pattern Recognit..

[5]  Takafumi Miyatake,et al.  Automatic Recognition of Engineering Drawings and Maps , 2020, Image Analysis Applications.

[6]  Leonardo Tanzi,et al.  Hierarchical fracture classification of proximal femur X-Ray images using a multistage Deep Learning approach. , 2020, European journal of radiology.

[7]  Chul-Jin Lee,et al.  Deep Neural Network for Automatic Image Recognition of Engineering Diagrams , 2020, Applied Sciences.

[8]  Germán H. Alférez,et al.  Image recognition of Legacy blueberries in a Chilean smart farm through deep learning , 2020, Comput. Electron. Agric..

[9]  Florian Arendt,et al.  Detecting Intentional Self-Harm on Instagram: Development, Testing, and Validation of an Automatic Image-Recognition Algorithm to Discover Cutting-Related Posts , 2020, Social Science Computer Review.

[10]  Hironobu Fujiyoshi,et al.  Deep learning-based image recognition for autonomous driving , 2019, IATSS Research.

[11]  Duhwan Mun,et al.  Features Recognition from Piping and Instrumentation Diagrams in Image Format Using a Deep Learning Network , 2019, Energies.

[12]  Eul-Bum Lee,et al.  A Digitization and Conversion Tool for Imaged Drawings to Intelligent Piping and Instrumentation Diagrams (P&ID) , 2019, Energies.

[13]  Pengcheng Jiang,et al.  Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network , 2019, Comput. Ind..

[14]  Lovekesh Vig,et al.  Automatic Information Extraction from Piping and Instrumentation Diagrams , 2019, ICPRAM.

[15]  Dhiraj Manohar Dhane,et al.  A review of recent advances in lane detection and departure warning system , 2018, Pattern Recognit..

[16]  Giansalvo Cirrincione,et al.  Understanding Abstraction in Deep CNN: An Application on Facial Emotion Recognition , 2017, IIH-MSP.

[17]  Brijendra Kumar Joshi,et al.  A Review Paper: Noise Models in Digital Image Processing , 2015, ArXiv.

[18]  Levent Burak Kara,et al.  From engineering diagrams to engineering models: Visual recognition and applications , 2011, Comput. Aided Des..

[19]  Lei Wang,et al.  AdaBoost with SVM-based component classifiers , 2008, Eng. Appl. Artif. Intell..

[20]  Ching Y. Suen,et al.  A fast parallel algorithm for thinning digital patterns , 1984, CACM.